ABSTRACT
The problem of signed network embedding (SNE) aims to represent nodes in a given signed network as low-dimensional vectors. While several SNE methods based on graph convolutional networks (GCN) have been proposed, we point out that they significantly rely on the assumption that the decades-old balance theory always holds in the real world. To address this limitation, we propose a novel GCN-based SNE approach, named as TrustSGCN, which measures the trustworthiness on edge signs for high-order relationships inferred by balance theory and corrects incorrect embedding propagation based on the trustworthiness. The experiments on four real-world signed network datasets demonstrate that TrustSGCN consistently outperforms five state-of-the-art GCN-based SNE methods. The code is available at https://github.com/kmj0792/TrustSGCN.
- Teresa Alsinet, Josep Argelich, Ramón Béjar, and Santi Martínez. 2021. Measuring polarization in online debates. Applied Sciences, Vol. 11, 24 (2021), 11879.Google ScholarCross Ref
- Omid Askarisichani, Jacqueline Ng Lane, Francesco Bullo, Noah E Friedkin, Ambuj K Singh, and Brian Uzzi. 2019. Structural balance emerges and explains performance in risky decision-making. Nature communications, Vol. 10, 1 (2019), 2648.Google Scholar
- Brigitte Boden, Stephan Gü nnemann, Holger Hoffmann, and Thomas Seidl. 2012. Mining coherent subgraphs in multi-layer graphs with edge labels. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD). 1258--1266.Google ScholarDigital Library
- Francesco Bonchi, Edoardo Galimberti, Aristides Gionis, Bruno Ordozgoiti, and Giancarlo Ruffo. 2019. Discovering Polarized Communities in Signed Networks. In Proceedings of the ACM International Conference on Information and Knowledge Management (CIKM). 961--970.Google ScholarDigital Library
- Dorwin Cartwright and Frank Harary. 1956. Structural balance: a generalization of Heider's theory. Psychological Review, Vol. 63, 5 (1956), 277.Google ScholarCross Ref
- Tyler Derr, Yao Ma, and Jiliang Tang. 2018. Signed Graph Convolutional Networks. In Proceedings of the IEEE International Conference on Data Mining (ICDM). 929--934.Google ScholarCross Ref
- Patrick Doreian and Andrej Mrvar. 2015. Structural Balance and Signed International Relations. Journal of Social Structure, Vol. 16, 1 (2015), 2.Google ScholarCross Ref
- Ernesto Estrada. 2019. Rethinking structural balance in signed social networks. Discrete Applied Mathematics, Vol. 268 (2019), 70--90.Google ScholarCross Ref
- James A Hanley and Barbara J McNeil. 1982. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology, Vol. 143, 1 (1982), 29--36.Google ScholarCross Ref
- Fritz Heider. 1946. Attitudes and cognitive organization. The Journal of Psychology, Vol. 21, 1 (1946), 107--112.Google ScholarCross Ref
- Junjie Huang, Huawei Shen, Liang Hou, and Xueqi Cheng. 2019. Signed Graph Attention Networks. In Proceedings of the International Conference on Artificial Neural Networks (ICANN), Vol. 11731. 566--577.Google ScholarDigital Library
- Junjie Huang, Huawei Shen, Liang Hou, and Xueqi Cheng. 2021. SDGNN: Learning Node Representation for Signed Directed Networks. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI). 196--203.Google ScholarCross Ref
- Zexi Huang, Arlei Silva, and Ambuj K. Singh. 2022. POLE: Polarized Embedding for Signed Networks. In Proceedings of the ACM International Conference on Web Search and Data Mining (WSDM). 390--400.Google Scholar
- Bei Hui, Lizong Zhang, Xue Zhou, Xiao Wen, and Yuhui Nian. 2022. Personalized recommendation system based on knowledge embedding and historical behavior. Applied Intelligence, Vol. 52, 1 (2022), 954--966.Google ScholarDigital Library
- Won-Seok Hwang, Juan Parc, Sang-Wook Kim, Jongwuk Lee, and Dongwon Lee. 2016. "Told you i didn't like it": Exploiting uninteresting items for effective collaborative filtering. In Proceedings of the IEEE International Conference on Data Engineering (ICDE). 349--360.Google ScholarCross Ref
- Vijay Ingalalli, Dino Ienco, and Pascal Poncelet. 2018. Mining frequent subgraphs in multigraphs. Information Sciences, Vol. 451--452 (2018), 50--66.Google ScholarCross Ref
- Thomas N. Kipf and Max Welling. 2016. Semi-Supervised Classification with Graph Convolutional Networks., Vol. abs/1609.02907 (2016).Google Scholar
- Wonchang Lee, Yeon-Chang Lee, Dongwon Lee, and Sang-Wook Kim. 2021. Look Before You Leap: Confirming Edge Signs in Random Walk with Restart for Personalized Node Ranking in Signed Networks. In Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR). 143--152.Google ScholarDigital Library
- Yeon-Chang Lee, Nayoun Seo, Kyungsik Han, and Sang-Wook Kim. 2020. ASiNE: Adversarial Signed Network Embedding. In Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR). 609--618.Google ScholarDigital Library
- Yeon-Chang Lee, Sang-Wook Kim, and Dongwon Lee. 2018. gOCCF: Graph-theoretic one-class collaborative filtering based on uninteresting items. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Vol. 32.Google ScholarCross Ref
- Yeon-Chang Lee, JaeHyun Lee, Dongwon Lee, and Sang-Wook Kim. 2022. THOR: Self-Supervised Temporal Knowledge Graph Embedding via Three-Tower Graph Convolutional Networks. In Proceedings of the IEEE International Conference on Data Mining (ICDM). 1035--1040.Google ScholarCross Ref
- Jure Leskovec, Daniel P. Huttenlocher, and Jon M. Kleinberg. 2010. Predicting positive and negative links in online social networks. In Proceedings of the ACM Web Conference (WWW). 641--650.Google Scholar
- Xiaoming Li, Hui Fang, and Jie Zhang. 2017. Rethinking the Link Prediction Problem in Signed Social Networks. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI). 4955--4956.Google ScholarCross Ref
- Yu Li, Yuan Tian, Jiawei Zhang, and Yi Chang. 2020. Learning Signed Network Embedding via Graph Attention. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI). 4772--4779.Google ScholarCross Ref
- Mathias Niepert, Mohamed Ahmed, and Konstantin Kutzkov. 2016. Learning Convolutional Neural Networks for Graphs. In Proceedings of the International Conference on Machine Learning (ICML), Vol. 48. 2014--2023.Google Scholar
- Lin Shu, Erxin Du, Yaomin Chang, Chuan Chen, Zibin Zheng, Xingxing Xing, and Shaofeng Shen. 2021. SGCL: Contrastive Representation Learning for Signed Graphs. In Proceedings of the ACM International Conference on Information and Knowledge Management (CIKM). 1671--1680.Google ScholarDigital Library
- Jiliang Tang, Charu C. Aggarwal, and Huan Liu. 2016a. Recommendations in Signed Social Networks. In Proceedings of the ACM Web Conference (WWW). 31--40.Google ScholarDigital Library
- Jiliang Tang, Yi Chang, Charu C. Aggarwal, and Huan Liu. 2016b. A Survey of Signed Network Mining in Social Media. Comput. Surveys, Vol. 49, 3 (2016), 42:1--42:37.Google Scholar
- Hongwei Wang, Fuzheng Zhang, Min Hou, Xing Xie, Minyi Guo, and Qi Liu. 2018. SHINE: Signed Heterogeneous Information Network Embedding for Sentiment Link Prediction. In Proceedings of the ACM International Conference on Web Search and Data Mining (WSDM). 592--600.Google ScholarDigital Library
- Suhang Wang, Jiliang Tang, Charu C. Aggarwal, Yi Chang, and Huan Liu. 2017. Signed Network Embedding in Social Media. In Proceedings of the SIAM International Conference on Data Mining (SDM). 327--335.Google ScholarCross Ref
- Pinghua Xu, Yibing Zhan, Liu Liu, Baosheng Yu, Bo Du, Jia Wu, and Wenbin Hu. 2022. Dual-branch Density Ratio Estimation for Signed Network Embedding. In Proceedings of the ACM Web Conference (WWW). 1651--1662.Google ScholarDigital Library
- Hyunsik Yoo, Yeon-Chang Lee, Kijung Shin, and Sang-Wook Kim. 2022. Directed Network Embedding with Virtual Negative Edges. In Proceedings of the ACM International Conference on Web Search and Data Mining (WSDM). 1291--1299.Google ScholarDigital Library
- Shuhan Yuan, Xintao Wu, and Yang Xiang. 2017. SNE: Signed Network Embedding. In Proceedings of Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD). 183--195.Google ScholarCross Ref
- He Zhang, Bang Wu, Xingliang Yuan, Shirui Pan, Hanghang Tong, and Jian Pei. 2022. Trustworthy graph neural networks: Aspects, methods and trends. arXiv preprint arXiv:2205.07424 (2022).Google Scholar
Index Terms
- TrustSGCN: Learning Trustworthiness on Edge Signs for Effective Signed Graph Convolutional Networks
Recommendations
Signed Network Modeling Based on Structural Balance Theory
CIKM '18: Proceedings of the 27th ACM International Conference on Information and Knowledge ManagementThe modeling of networks, specifically generative models, has been shown to provide a plethora of information about the underlying network structures, as well as many other benefits behind their construction. There has been a considerable increase in ...
Signed Graph Attention Networks
Artificial Neural Networks and Machine Learning – ICANN 2019: Workshop and Special SessionsAbstractGraph or network data is ubiquitous in the real world, including social networks, information networks, traffic networks, biological networks and various technical networks. The non-Euclidean nature of graph data poses the challenge for modeling ...
SigGAN: Adversarial Model for Learning Signed Relationships in Networks
Signed link prediction in graphs is an important problem that has applications in diverse domains. It is a binary classification problem that predicts whether an edge between a pair of nodes is positive or negative. Existing approaches for link prediction ...
Comments